BestHub
Sign in
Data Party THU
Author

Data Party THU

Official platform of Tsinghua Big Data Research Center, sharing the team's latest research, teaching updates, and big data news.

546
Articles
1
Likes
3.5k
Views
0
Comments
Recent Articles

Latest from Data Party THU

100 recent articles max
Data Party THU
Data Party THU
Sep 10, 2026 · Artificial Intelligence

Harness Continual Learning: How Agents Evolve Without Model Fine-Tuning

Researchers from Nanjing University and University of Wollongong propose Harness Continual Learning (HCL), a framework where AI agents continuously adapt by evolving their system-level harness—prompts, memory, skills, tools, and routing—while keeping the base model frozen, demonstrating improved performance and controlled forgetting across diverse benchmarks.

ALFWorldAgent Continual LearningDeepSeek-V4
0 likes · 16 min read
Harness Continual Learning: How Agents Evolve Without Model Fine-Tuning
Data Party THU
Data Party THU
Sep 9, 2026 · Artificial Intelligence

Online and Off-Policy Learning for Large Action Spaces: Structured Exploration & Optimization

This PhD thesis addresses large action space contextual bandits, proposing mixed-effects and diffusion Thompson sampling for online learning, and structured direct methods, policy-weighted likelihood, exponential smoothing, and PAC-Bayes pessimism for offline learning, showing that action structure, optimizable objectives, and pessimism are crucial for scalable decision-making.

Offline Policy LearningPAC-BayesThompson sampling
0 likes · 21 min read
Online and Off-Policy Learning for Large Action Spaces: Structured Exploration & Optimization
Data Party THU
Data Party THU
Sep 6, 2026 · Artificial Intelligence

Inside the DOE's Genesis Mission: 278 Projects Building AI as Scientific Infrastructure

The U.S. Department of Energy's Genesis Mission selected 278 Phase I projects from over 5,000 applications to integrate AI with supercomputing and scientific instruments, showcasing three examples: GPU-accelerated Monte Carlo for LHC, cross-scale plasma dynamics discovery, and AI agents for high-energy physics analysis at CERN.

AI agentsAI for scienceCERN
0 likes · 10 min read
Inside the DOE's Genesis Mission: 278 Projects Building AI as Scientific Infrastructure
Data Party THU
Data Party THU
Sep 5, 2026 · Artificial Intelligence

TinySR: Lightweight Diffusion for Real-World Super-Resolution, 5.68x Faster

TinySR introduces a lightweight diffusion transformer for real-world image super-resolution, achieving 5.68x inference speedup and 83% parameter reduction over its teacher model TSD-SR through learnable pruning, dynamic block activation, VAE compression, and removal of time/prompt modules, while maintaining competitive perceptual quality on benchmarks.

TinySRVAE lightweightingdiffusion model
0 likes · 17 min read
TinySR: Lightweight Diffusion for Real-World Super-Resolution, 5.68x Faster
Data Party THU
Data Party THU
Sep 3, 2026 · Databases

Sonar-TS: Training-Free Natural Language Querying for Massive Time Series Databases

Sonar-TS introduces a training-free framework for natural language querying of massive time series databases, defining the new NLQ4TSDB problem, creating the NLQTSBench benchmark, and using a search-then-verify approach with symbolic indexing and code-based verification to find pattern matches across millions of data points.

NLQ4TSDBNLQTSBenchSonar-TS
0 likes · 12 min read
Sonar-TS: Training-Free Natural Language Querying for Massive Time Series Databases
Data Party THU
Data Party THU
Sep 1, 2026 · Artificial Intelligence

How OVOW Turns Monocular Video into Physically Simulatable 4D Meshes

OVOW introduces a pipeline that converts ordinary monocular video into instance‑level 4D meshes with real‑world scale, motion, and physical properties, enabling direct editing and simulation in physics engines while outperforming prior 4D reconstruction methods in accuracy and speed.

4D reconstructionECCV 2026OVOW
0 likes · 9 min read
How OVOW Turns Monocular Video into Physically Simulatable 4D Meshes
Data Party THU
Data Party THU
Aug 31, 2026 · Industry Insights

How AI Is Becoming a Lab Partner: From Material Design to Automated Experiments

The article examines the emerging trend of autonomous science, highlighting how AI systems like CuspAI and PNNL are moving beyond data analysis to propose research directions, design experiments, and control laboratory equipment, aiming to accelerate material discovery while addressing challenges of data complexity and real‑world impact.

AIAutonomous ScienceCuspAI
0 likes · 6 min read
How AI Is Becoming a Lab Partner: From Material Design to Automated Experiments
Data Party THU
Data Party THU
Aug 30, 2026 · Artificial Intelligence

Foundations and Frontiers of Multimodal Agentic Frameworks: A Comprehensive Survey

This survey systematically maps the core modules, technical lineage, and emerging applications of multimodal agentic frameworks, detailing perception, orchestration, and action components, taxonomy of multimodal fusion strategies, performance bottlenecks, efficiency tricks, scalability challenges, latency sources, safety risks, current limitations, and promising future research directions.

ActionAgentic FrameworksEfficiency
0 likes · 21 min read
Foundations and Frontiers of Multimodal Agentic Frameworks: A Comprehensive Survey